[1]李松宇.基于 HED—UNet 遥感图像建筑物语义分割[J].计算机技术与发展,2022,32(S2):58-63.[doi:10. 3969 / j. issn. 1673-629X. 2022. S2. 010]
　LI Song-yu.Semantic Segmentation of Buildings in Remote Sensing Images Based on HED-UNet[J].,2022,32(S2):58-63.[doi:10. 3969 / j. issn. 1673-629X. 2022. S2. 010]
点击复制

基于 HED—UNet 遥感图像建筑物语义分割()

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
32
期数:
2022年S2期
页码:
58-63
栏目:
图形与图像
出版日期:
2022-12-11

文章信息/Info

Title:
Semantic Segmentation of Buildings in Remote Sensing Images Based on HED-UNet
文章编号:
1673-629X(2022)S2-0058-06
作者:
李松宇
渤海大学 信息科学与技术学院,辽宁 锦州 121000
Author(s):
LI Song-yu
School of Information Science and Technology,Bohai University,Jinzhou 121000,China
关键词:
语义分割; 遥感图像; 深度学习; U-Net 网络; HED-UNet
Keywords:
semantic segmentation; remote sensing image; deep learning; U-Net; HED-UNet
分类号:
TP31
DOI:
10. 3969 / j. issn. 1673-629X. 2022. S2. 010
摘要:
作为计算机视觉领域的关键问题之一,语义分割通过对每个像素进行密集的预测并推断标签来实现细粒度的推理。 而针对遥感图像中建筑物的语义分割能够节省大量人力和时间成本。 但现有语义分割技术,往往经过多次下采样,使得目标细节特征损失严重。 该文将最新的 HED-UNet 网络迁移到针对遥感图像建筑物的语义分割中来。 HED 网络是一个多尺度融合网络,带有深度监督机制。 将 HED 网络嵌入到 U-Net 网络中,通过在多分辨率下对侧输出预测进行深度监督,使训练更为有效。 并引入一种层级注意机制,将这些多尺度预测自适应地合并到最终的模型输出中。 最后,在武汉大学的遥感建筑物数据集上进行了实验研究,结果表明 HED-UNet 相比于传统语义分割网络性能提升明显,PA 达到了0郾 966,MIoU 达到了 0. 922。
Abstract:
As one of the key issues in the field of computer vision, semantic segmentation implements fine - grained reasoning byintensively predicting each pixel and inferring labels. The semantic segmentation of buildings in remote sensing images can save a lot ofmanpower and time costs. However,the existing semantic segmentation technology often undergoes multiple downsampling,resulting inserious loss of target detail features. This article migrates the latest HED-UNet network to the semantic segmentation of remote sensingimage buildings. The HED network is a multi-scale fusion network with a deep supervision mechanism. The HED network is embeddedin the U-Net network,and the training is more effective through deep supervision of the side output prediction under multi-resolution.And introduce a hierarchical attention mechanism to adaptively incorporate these multi - scale predictions into the final model output.Finally, an experimental study was conducted on the remote sensing building data set of Wuhan University. The results showed thatcompared with traditional semantic segmentation network,the performance of HED-UNet was significantly improved,with PA reaching96. 6% and MIoU reaching 92. 2% .

相似文献/References:

[1]蒋璐璐 王适 王宝成 李慧敏 李鑫慧.一种改进的标记分水岭遥感图像分割方法[J].计算机技术与发展,2010,(01):36.
　JIANG Lu-lu,WANG Shi,WANG Bao-cheng,et al.Segmentation of Remote Sensing Image Based on an Improved Labeling Watershed Algorithm[J].,2010,(S2):36.
[2]赵艳飞 高清维 卢一相.基于多尺度Retinex算法的遥感图像增强[J].计算机技术与发展,2008,(02):70.
　ZHAO Yan-fei,GAO Qing-wei,LU Yi-xiang.Remote Sensing Image Enhancement Based on Multi- Scale Retinex Algorithm[J].,2008,(S2):70.
[3]陈昌生 许文波 赵健.基于ArcSDE的卫星遥感影像数据库研究[J].计算机技术与发展,2010,(07):80.
　CHEN Chang-sheng,XU Wen-bo,ZHAO Jian.Research on Remote Sensing Image Database Based on ArcSDE[J].,2010,(S2):80.
[4]李晓飞 马大玮 范小麟 胡焰智.基于数学形态学的遥感图像多感兴趣区域提取[J].计算机技术与发展,2007,(12):56.
　LI Xiao-fei,MA Da-wei,FAN Xiao-lin,et al.Extraction of ROIs Based on Mathematical Morphology toward Applications on Remote Sense Image Processing[J].,2007,(S2):56.
[5]董敏[],阎镇.基于CUDA的航天遥感图像实时快视系统的研究[J].计算机技术与发展,2014,24(06):32.
　DONG Min[][][],YAN Zhen[].Research on Aerospace Remote Sensing Images Real-time Quick-view System Based on CUDA[J].,2014,24(S2):32.
[6]张亚亚,张立民,刘小伟,等. 基于语义网的遥感图像分类[J].计算机技术与发展,2015,25(05):218.
　ZHANG Ya-ya,ZHANG Li-min,LIU Xiao-wei,et al. Remote Sensing Image Classification Based on Semantic-net[J].,2015,25(S2):218.
[7]黄涛[][],薛丰昌[],钱洪亮[],等. 基于 NSCT 和自适应模糊阈值遥感图像去噪算法[J].计算机技术与发展,2016,26(01):65.
　HUANG Tao[][],XUE Feng-chang[],QIAN Hong-liang[],et al. Remote Sensing Image Denoising Algorithm Based on NSCT and Adaptive Fuzzy Threshold[J].,2016,26(S2):65.
[8]龚林松,李士进.基于改进的SLIC和OTSU的遥感影像水体提取[J].计算机技术与发展,2019,29(01):145.[doi:10. 3969 / j. issn. 1673-629X. 2019. 01. 030]
　GONG Lin-song,LI Shi-jin.Water Information Extraction from Remote Sensing Imagery Based onImproved SLIC and OTSU[J].,2019,29(S2):145.[doi:10. 3969 / j. issn. 1673-629X. 2019. 01. 030]
[9]朱小明.基于多光谱遥感图像信息的水质污染监测研究[J].计算机技术与发展,2018,28(11):52.[doi:10.3969/ j. issn.1673-629X.2018.11.012]
　ZHU Xiao-ming.Research on Water Quality Monitoring Based on Multi-spectral Remote Sensing Imagery[J].,2018,28(S2):52.[doi:10.3969/ j. issn.1673-629X.2018.11.012]
[10]岳钦崟,李 虎.基于 MPI 并行遥感典型地类提取应用[J].计算机技术与发展,2020,30(07):104.[doi:10. 3969 / j. issn. 1673-629X. 2020. 07. 023]
　YUE Qin-yin,LI Hu.Application of MPI-based Parallel Remote Sensing for Typical Ground Classification Extraction[J].,2020,30(S2):104.[doi:10. 3969 / j. issn. 1673-629X. 2020. 07. 023]
[11]王学伟.基于递归特征与边缘解耦的遥感图像语义分割[J].计算机技术与发展,2025,(03):40.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0325]
　WANG Xue-wei.Semantic Segmentation of Remote Sensing Images Based on Recursive Features and Edge Decoupling[J].,2025,(S2):40.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0325]
[12]于攀琳,吴旭*,张凌云,等.增强特征提取和解释的遥感图像语义分割模型[J].计算机技术与发展,2025,(07):8.[doi:10.20165/j.cnki.ISSN1673-629X.2025.0039]
　YU Pan-lin,WU Xu*,ZHANG Ling-yun,et al.A Semantic Segmentation Model for Remote Sensing Images with Enhanced Feature Extraction and Interpretation[J].,2025,(S2):8.[doi:10.20165/j.cnki.ISSN1673-629X.2025.0039]

更新日期/Last Update: 2022-10-10